ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)

Cisco bypassed bioweapon guardrails on ChatGPT, Claude, and Gemini within five conversational turns. Attack success rates across 15 models from OpenAI, Anthropic, Google, Amazon, and xAI ranged from 8% to 88%.
Tap to vote and see what everyone thinks.
Summary by ByteBrief